happy-horse-dynamic-comic-video

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated video and image files from the service's API endpoints (ai-hive.iclip.cn) to the user's local ~/Downloads/AiHive directory.
  • [COMMAND_EXECUTION]: Execution of the provided videogen.py script is required to interact with the generation service. The script handles HTTP requests, file system writes, and interactive configuration setup via the init command.
  • [DATA_EXPOSURE]: The skill manages an API key stored in ~/.ai-hive/config.json. The script includes logic to set secure file permissions (0600) for this configuration file, which is a security best practice for local secret management.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external inputs (user-provided prompts and media files) to be processed by an AI model. While these are processed by the external service as intended, they represent an entry point for untrusted data typical of AI generation workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:20 PM
Security Audit — agent-trust-hub — happy-horse-dynamic-comic-video